Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He sat on the park bench, watching the leaves fall. The crisp air did little to invigorate him. He should be studying, he should be fighting the accusations. But the energy simply wasn't there. It felt like a battle he'd already lost.

The wind rustled the trees, a constant, mournful whisper. He pulled his jacket tighter around him, the fabric doing little to fend off the cold that had settled deep inside. The accusations, the denial, the eventual punishment – it was a predictable script.

He pulled a cigarette from his pocket, his hand shaking slightly as he lit it. The smoke tasted acrid. He let it burn, watching the ash crumble onto the ground, just another detail lost to time.

Emotion: resigned

Cluster: Passivity
PC1 (Valence): -0.75 Negative
PC2 (Disposition): 0.16

Role in Research

This story is one of 1,000 stories generated for the emotion resigned. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 resigned stories, after denoising with neutral dialogue baselines, produces the resigned emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the resigned vector is projected through the unembedding matrix.

Promoted:
S0.437
a0.351
que0.323
வதில்லை0.267
sighed0.265
Suppressed:
C-0.375
!-0.316
인해-0.310
Furthermore-0.298
🤩-0.296